Diffusion Removes Langevin's Conditioning Dependence: A Sharp Gaussian Analysis
Despite their empirical success, why diffusion models overcome the bottlenecks of classical score-based samplers remains unclear. In this work, we leverage Gaussian distributions to isolate this phenomenon.
By Adam Perbost, Francis Bach, Pierre MarionarXiv - stat.ML
Read the full story
Originally published by arXiv - stat.ML on Oct 9, 2026.
Comments
Sign in to join the discussion.